.png){kind=icon}
.png){kind=icon}
Return
Polynomial fitting-based shape matching algorithm for multi-sensors remote sensing images
.png){kind=icon}
PRE
AI
DOI：10.1016/j.infrared.2016.03.019.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
According to the characteristics of multi-sensors remote sensing images, a new registration algorithm based on shape contour feature is proposed. Firstly, the edge features of remote sensing images are extracted by Canny operator, and the edge of the main contour is retained. According to the characteristics of the contour pixels, a new feature extraction algorithm based on polynomial fitting is proposed and it is used to determine the principal directions of the feature points. On this basis, we improved the shape context descriptor and completed coarse registration by minimizing the matching cost between the feature points. The shape context has been found to be robust in Simple object registration, and in this paper, it is applied to remote sensing image registration after improving the circular template with rotation invariance. Finally, the fine registration is accomplished by the RANSAC algorithm. Experiments show that this algorithm can realize the automatic registration of multi-sensors remote sensing images with high accuracy, robustness and applicability. (C) 2016 Elsevier B.V. All rights reserved.
Keywords:
Shape matching
Remote sensing
Multi-sensors
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
I
IF:
3.4
Papers:
5.8K
Citations:
1.2W
Organization
No organization information available